CN110175963A - It is a kind of suitable for underwater picture and the dual-purpose image enchancing method and device of the dark image of atmosphere - Google Patents
It is a kind of suitable for underwater picture and the dual-purpose image enchancing method and device of the dark image of atmosphere Download PDFInfo
- Publication number
- CN110175963A CN110175963A CN201910453495.6A CN201910453495A CN110175963A CN 110175963 A CN110175963 A CN 110175963A CN 201910453495 A CN201910453495 A CN 201910453495A CN 110175963 A CN110175963 A CN 110175963A
- Authority
- CN
- China
- Prior art keywords
- image
- atmosphere
- underwater picture
- incident light
- reflectivity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000012937 correction Methods 0.000 claims abstract description 17
- 230000002708 enhancing effect Effects 0.000 claims abstract description 17
- 238000002310 reflectometry Methods 0.000 claims description 57
- 238000012217 deletion Methods 0.000 claims description 7
- 230000037430 deletion Effects 0.000 claims description 7
- 238000012805 post-processing Methods 0.000 claims description 7
- 230000001105 regulatory effect Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 description 12
- 238000004364 calculation method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000000354 decomposition reaction Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 238000000889 atomisation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 108010054616 clipsin Proteins 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000004297 night vision Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000003389 potentiating effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of suitable for underwater picture and the dual-purpose image enchancing method and device of the dark image of atmosphere, this method comprises: receiving the original image and grayscale image of the dark image of underwater picture or atmosphere to image enhancement；Estimated by the target equation of building, obtains albedo image and incident light images；Albedo image degree of comparing is enhanced, the atmosphere image of high brightness is obtained；Colour correction is carried out to incident light images, the underwater picture enhanced in conjunction with contrast enhancing result.It can be not only used for correcting underwater picture colour cast, improve underwater picture contrast, and can be used for enhancing the dark image shot in atmosphere.
Description
Technical field
The disclosure belongs to the technical field of image procossing, is related to a kind of suitable for the dual-purpose of underwater picture and the dark image of atmosphere
Image enchancing method and device.
Background technique
Only there is provided background technical informations relevant to the disclosure for the statement of this part, it is not necessary to so constitute first skill
Art.
Underwater picture is one of the means that the mankind obtain underwater effective information, the eased portable, acquisition of photoimaging systems
Speed is fast, axis information is abundant, so that Underwater Optical is imaged as the main obtaining means of underwater picture.The dark image of atmosphere is low illumination
Under the conditions of the image that shoots, in night vision monitoring, low dose X-ray such as are imaged at the practical applications, by imaging h ardware and
Imaging circumstances influence, our the getable images of institute are usually the dark image of atmosphere.
However, inventor has found in R&D process, the image obtained under water has that fuzzy, colour cast, contrast are low etc. to be lacked
It falls into；And in atmospheric environment, the image table shot under low-light conditions reveals darker brightness, and the details of dark scene is caused to lose
It loses, these two types of image tables reveal different low-quality flow characteristics.
Summary of the invention
Can not achieve underwater picture for the prior art and the case where the dark image of atmosphere enhances simultaneously, one of the disclosure or
Multiple embodiments provide a kind of suitable for underwater picture and the dual-purpose image enchancing method and device of the dark image of atmosphere, both can be used
In correcting underwater picture colour cast, improve underwater picture contrast, and can be used for enhancing the dark image shot in atmosphere.
According to the one aspect of one or more other embodiments of the present disclosure, provide a kind of dark suitable for underwater picture and atmosphere
The dual-purpose image enchancing method of image.
It is a kind of suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere, this method comprises:
Receive the original image and grayscale image of the dark image of underwater picture or atmosphere to image enhancement；
Estimated by the target equation of building, obtains albedo image and incident light images；
Albedo image degree of comparing is enhanced, the atmosphere image of high brightness is obtained；
Colour correction is carried out to incident light images, the underwater picture enhanced in conjunction with contrast enhancing result.
Further, in the method, by the RGB tri- to the underwater picture of image enhancement or the original image of the dark image of atmosphere
The target equation that channel passes through building respectively is estimated.
Further, in the method, the target equation is constructed according to Retinex theory, the target equation is anti-
It penetrates rate and the data holding item of incident light, the sparse regularization term of full variation, the data of reflectivity keeps the number of item and incident light
According to the sum of holding item；The restrictive condition of the target equation is that reflectivity value range is [0 1]；
The data of the reflectivity and incident light holding item subtracts the L2 model of original image by the product of reflectivity and incident light
Number indicates；
The sparse regularization term of full variation is indicated by the L1 norm of gradient operator and reflectivity product；
The data of the reflectivity keep item to indicate by the L2 norm that reflectivity subtracts grayscale image；
The data of the incident light keep item to be mapped by the Steerable filter that incident light subtracts original image by [0 1] intervals linear
L2 norm to [0.2 1] section indicates.
Further, this method further include: be introduced into auxiliary variable Z, E and regulatory factor ρ in the target equation
The L1 norm of the sparse regularization term of full variation carries out equivalent transformation, supplemented by the transformed complete sparse regularization term of variation
Help the L1 norm of variable Z and gradient operator and reflectivity product subtract auxiliary variable Z add the L2 norm of auxiliary variable E and adjust because
The sum of products of sub- ρ.
Further, in the method, transformed target equation is decomposed into Z subproblem, R subproblem and I subproblem
Loop iteration solution is carried out, and reflectivity and incident light are modified according to restrictive condition, obtains albedo image and incidence
Light image.
Further, in the method, the Z subproblem be by transformed target equation be free of Z entry deletion, and
The optimal solution of Z subproblem is exported by shrinkage operation；
The R subproblem be by transformed target equation be free of R entry deletion, and by enable R partial derivative be 0,
It is solved using Fast Fourier Transform (FFT) and in conjunction with convolution theorem, obtains the optimal solution of R subproblem；
The I subproblem be by transformed target equation be free of I entry deletion, and by enable I partial derivative be 0,
Obtain the optimal solution of I subproblem.
Further, in the method, albedo image increases its radio-frequency component degree of comparing using homomorphic filtering
By force.
Further, in the method, colour correction is carried out using Gaussian Profile Linear Mapping to incident light images.
According to the one aspect of one or more other embodiments of the present disclosure, a kind of computer readable storage medium is provided.
A kind of computer readable storage medium, wherein being stored with a plurality of instruction, described instruction is suitable for by terminal device
Reason device load and a kind of described in executing is suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere.
According to the one aspect of one or more other embodiments of the present disclosure, a kind of terminal device is provided.
A kind of terminal device comprising processor and computer readable storage medium, processor is for realizing each instruction；Meter
Calculation machine readable storage medium storing program for executing is suitable for being loaded by processor and being executed described one kind and is applicable in for storing a plurality of instruction, described instruction
In underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere.
According to the one aspect of one or more other embodiments of the present disclosure, provide a kind of dark suitable for underwater picture and atmosphere
The dual-purpose image intensifier device of image.
It is a kind of suitable for underwater picture and the dual-purpose image intensifier device of the dark image of atmosphere, be suitable for based on described one kind
The dual-purpose image enchancing method of underwater picture and the dark image of atmosphere, comprising:
Image receiver module is configured as receiving the original image and ash of the dark image of underwater picture or atmosphere to image enhancement
Degree figure；
Reflectivity and incident light estimation module are configured as being estimated by the target equation of building, obtain reflectivity
Image and incident light images；
Reflectivity post-processing module is configured as enhancing albedo image degree of comparing, obtains the atmosphere of high brightness
Image；
Incident light post-processing module, is configured as carrying out colour correction to incident light images, enhances result in conjunction with contrast
The underwater picture enhanced.
The disclosure the utility model has the advantages that
The disclosure provides a kind of suitable for underwater picture and the dual-purpose image enchancing method and device of the dark image of atmosphere, root
According to prior information, is estimated by the target equation of building, obtain albedo image and incident light images；Respectively to reflectivity
The enhancing of image degree of comparing, obtains the atmosphere image of high brightness；Colour correction is carried out to incident light images, is increased in conjunction with contrast
The underwater picture that strong result is enhanced.The disclosure can be not only used for correcting underwater picture colour cast, improve underwater picture contrast, again
It can be used for enhancing the dark image shot in atmosphere.
Detailed description of the invention
The accompanying drawings constituting a part of this application is used to provide further understanding of the present application, and the application's shows
Meaning property embodiment and its explanation are not constituted an undue limitation on the present application for explaining the application.
Fig. 1 is to be increased according to a kind of of one or more embodiments suitable for the dual-purpose image of underwater picture and the dark image of atmosphere
Strong method flow chart；
Fig. 2 is according to the specific a kind of suitable for the dual-purpose of underwater picture and the dark image of atmosphere of one or more embodiments
Image enchancing method flow chart；
Fig. 3 is the dark image schematic diagram of atmosphere after the dark image of atmosphere and image enhancement according to one or more embodiments；
Fig. 4 is the underwater picture schematic diagram after underwater picture and image enhancement according to one or more embodiments.
Specific embodiment:
Below in conjunction with the attached drawing in one or more other embodiments of the present disclosure, to one or more other embodiments of the present disclosure
In technical solution be clearly and completely described, it is clear that described embodiments are only a part of the embodiments of the present invention,
Instead of all the embodiments.Based on one or more other embodiments of the present disclosure, those of ordinary skill in the art are not being made
Every other embodiment obtained, shall fall within the protection scope of the present invention under the premise of creative work.
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the application.Unless another
It indicates, all technical and scientific terms that the present embodiment uses have and the application person of an ordinary skill in the technical field
Normally understood identical meanings.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root
According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singular
Also it is intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or their combination.
It should be noted that flowcharts and block diagrams in the drawings show according to various embodiments of the present disclosure method and
The architecture, function and operation in the cards of system.It should be noted that each box in flowchart or block diagram can represent
A part of one module, program segment or code, a part of the module, program segment or code may include one or more
A executable instruction for realizing the logic function of defined in each embodiment.It should also be noted that some alternately
Realization in, function marked in the box can also occur according to the sequence that is marked in attached drawing is different from.For example, two connect
The box even indicated can actually be basically executed in parallel or they can also be executed in a reverse order sometimes,
This depends on related function.It should also be noted that each box and flow chart in flowchart and or block diagram
And/or the combination of the box in block diagram, the dedicated hardware based system that functions or operations as defined in executing can be used are come
It realizes, or the combination of specialized hardware and computer instruction can be used to realize.
In the absence of conflict, the feature in the embodiment and embodiment in the disclosure can be combined with each other, and tie below
It closes attached drawing and embodiment is described further the disclosure.
Embodiment one
According to the one aspect of one or more other embodiments of the present disclosure, provide a kind of dark suitable for underwater picture and atmosphere
The dual-purpose image enchancing method of image.
As shown in Figure 1, a kind of suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere, this method packet
It includes:
It is a kind of suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere, this method comprises:
S1: the original image and grayscale image of the dark image of underwater picture or atmosphere to image enhancement are received；
S2: estimated by the target equation of building, obtain albedo image and incident light images；
S3: albedo image degree of comparing is enhanced, the atmosphere image of high brightness is obtained；
S4: carrying out colour correction to incident light images, the underwater picture enhanced in conjunction with contrast enhancing result.
According to Retinex theory, an image is represented by the product of reflectivity and incident light, as shown in formula (1).This
Patent uses the model, innovatively constructs target equation, while estimating reflectivity and incident light, and according to reflectivity and enters
The characteristic for penetrating light, respectively post-processes it, to export the image of enhancing.
Sc(x)=Rc(x)·Ic(x)c∈{r,g,b} (1)
S in formulacIt (x) is input picture (underwater picture or the dark image of atmosphere), Rc(x) reflectivity, I are indicatedc(x) indicate into
Light is penetrated, x indicates that pixel coordinate, c indicate image RGB triple channel, and ' ' representing matrix element is corresponding to be multiplied.
The method of proposition includes two big steps: S2 constructs target equation, estimates reflectivity and incident light；S3 and S4 difference
Reflectivity and incident light are post-processed, method flow is as shown in Figure 2.
In the step S2 of the present embodiment, by the RGB to the underwater picture of image enhancement or the original image of the dark image of atmosphere
The target equation that triple channel passes through building respectively is estimated.
Target equation is constructed in the method, the target equation is constructed according to Retinex theory, the target equation is
The data of reflectivity and incident light keep item, the sparse regularization term of full variation, the data of reflectivity holding item and incident light
Data keep the sum of item；The restrictive condition of the target equation is that reflectivity value range is [0 1]；
The data of the reflectivity and incident light holding item subtracts the L2 norm of original image by reflectivity and incident light product
It indicates；
The sparse regularization term of full variation is indicated by the L1 norm of gradient operator and reflectivity product；
The data of the reflectivity keep item to indicate by the L2 norm that reflectivity subtracts grayscale image；
The data of the incident light keep item to be mapped by the Steerable filter that incident light subtracts original image by [0 1] intervals linear
L2 norm to [0.2 1] section indicates.
Based on the model that formula (1) indicates, and according to prior information, target equation is innovatively constructed, such as formula (2) institute
Show and (to be easy to read, remove the identifier x of pixel coordinate in the formula of this section):
‖ ‖ in formula2Indicate L2 norm, | |1Indicate L1 norm, S is input picture (single channel), and I is incident light (single channel
Figure), R is reflectivity (single channel figure),Indicate gradient operator, α, beta, gamma is that regulatory factor (be shown in by fixed constant, specific value
Algorithm-1), G is the grayscale image of input picture.The value range of R is [0 1] section, so the restricted item of target equation
Part R≤1, items are described as follows in target equation:
Item is kept for the data of reflectivity R and incident light I, the product of R and I after limitation decomposition connect with S
Closely.
For the sparse regularization term of full variation, for preventing the reflectivity after decomposing doing over-sharpening.
Item is kept for the data of reflectivity R, the grayscale image G of R and input picture after limiting decomposition connect
Closely.There are two key effects by this, so that reflectivity R is kept the gradient information of original image, on the other hand make the three of output
A channel reflection rate R is close with G, and colour cast effect is transferred in incident light I indirectly.
Keep item for the data of incident light I, I after limiting decomposition withClose, this can make original image
The colour cast of picture is transferred in incident light I.Calculation method such as formula (3) shown in:
S in formulacFor input picture, GF () indicates Steerable filter, imadjustIndicating will figure
Picture[0.2 1] section (can be realized with matlab library function imadjust) is mapped to by [0 1] intervals linear.BecauseFor
Single channel figure, therefore calculateWhen only input S every timecIn corresponding single channel.The implementation of the calculation method allows for two
A prior information: incident light is more smooth and continuous in local smaller area；Absolute dark area is not present in reality, compared with
Also there is certain incident light in dark region.
Further, this method further include: be introduced into auxiliary variable Z, E and regulatory factor ρ in the target equation
The L1 norm of the sparse regularization term of full variation carries out equivalence transformation, supplemented by the transformed complete sparse regularization term of variation
Help the L1 norm of variable Z and gradient operator and reflectivity product subtract auxiliary variable Z add the L2 norm of auxiliary variable E and adjust because
The sum of products of sub- ρ.
In the present embodiment, auxiliary variable Z, E and regulatory factor ρ are introduced in order to solve L1 norm, and by formula (2)
The target equation of expression is transformed to formula (4):
s.t.R≤1
Further, in the method, transformed target equation is decomposed into Z subproblem, R subproblem and I subproblem
Loop iteration solution is carried out, and reflectivity and incident light are modified according to restrictive condition, obtains albedo image and incidence
Light image.
Z subproblem: the variable unrelated with Z is 0 to the partial derivative of Z, therefore the entry deletion that will be free of Z, obtains Z subproblem target
Function:
K indicates kth time iterative process in formula.The optimal solution of Z subproblem can be exported by shrinkage operation, such as formula (6) institute
Show:
R subproblem: deleting the item for being free of R, obtain R subproblem objective function, as shown in formula (7):
It is 0 that R, which is sought partial derivative and enabled, the optimal solution of R subproblem can be obtained, to avoid large-scale matrix inversion operation, using fast
Fast Fourier transformation is simultaneously solved in conjunction with convolution theorem, shown in the optimum results of R subproblem such as formula (8):
F indicates Fast Fourier Transform (FFT), F in formula-1For inverse Fourier transform, D is indicated and gradient operatorCorresponding convolution
Template, DTIndicate the transposed matrix of D.After the completion of R subproblem, E is updated by formula (9):
I subproblem: deleting the item for being free of I, obtain I subproblem objective function, as shown in formula (10):
It is 0 that I, which is sought partial derivative and enabled, can obtain the optimal solution of I subproblem, as shown in formula (11):
It by restrictive condition R≤1 of target equation, brings into formula (1), exports restrictive condition S≤I, therefore in each iteration
I and R need to be modified, as shown in formula (12):
Target equation Optimization Steps shown in formula (4) are embodied as shown in Algorithm-1:
Algorithm-1 is respectively executed to the RGB triple channel of input picture, obtains triple channel RcWith Ic.Because of incident light
IcComprising most of colour cast effect, therefore color correction post-processing is carried out to incident light；Reflectivity mainly includes the structure of original image
Information, gradient information, therefore its radio-frequency component is enhanced using homomorphic filtering.
Further, in the method, albedo image increases its radio-frequency component degree of comparing using homomorphic filtering
By force.
The reflectivity R of Algorithm-1 outputcMain includes the detailed information of original image, is radio-frequency component.And homomorphism is filtered
When enhancing high fdrequency component, can decay wave low frequency component, can combine global contrast and local contrast, therefore use homomorphism
It filters to improve the contrast of reflectivity.As shown in formula (13)-(16):
Rc(u)=F [ln Rc(x)] (13)
Q (u)=(θH-θL)[1-exp(-σD2(u)/D0)]+θL (16)
In formulaFor the reflectivity after homomorphic filtering, ln expression takes logarithm, by Rc(x) it is transformed into log-domain, F is fast
Fast Fourier transformation, F-1For inverse Fourier transform.Q (u) is filter, θH,θL,D0, σ is filter parameter, works as θL≤ 1 and θH
When >=1, filter enhances high fdrequency component, while low frequency component of decaying.Because being largely radio-frequency component in reflectivity, therefore by θH
It is set as 1.3, θLIt is set as 0.99.D0It is band logical radius and variance with σ, default setting is 200 and 2.In order to very dark atmosphere
Image also has reinforcing effect, using linear stretch to the image after homomorphic filteringIt is handled, to improve reflectivity
Brightness, as shown in formula (17):
In formulaFor the enhanced reflectivity of contrast,It indicates linear stretch, clipsIn
1% maximum pixel, and linearly it is stretched to [0 1] section.
Colour cast effect is not present in dark image in atmosphere, without carrying out color correction.Therefore, if input picture is that atmosphere is dark
Image, it is so far then exportable enhanced as a result, dark image enhancement effects are as shown in Figure 3.
Further, in the method, colour correction is carried out using Gaussian Profile Linear Mapping to incident light images.
There are colour casts for most of underwater picture, if input is underwater picture, need to carry out color correction.This patent is using high
This distribution Linear Mapping is to incident light IcColor correction is carried out, as shown in formula (18)-(20):
In formulaFor the incident light after color correction,Respectively input picture ScIn each channel RGB
Mean value and standard deviation.λ is regulatory factor, and for gauss of distribution function, the probability that sample is fallen in 3 times of standard deviations is
99.7%, cover most of sample, therefore λ takes 3.imadjust([0 1], [0.1 1], 0.4) expression pairIt carries out
Nonlinear Mapping is to improve incident brightness (can be realized with matlab library function imadjust).
Calculate the incident light of color correctionWith the reflectivity of contrast enhancingAfterwards, it can get enhancing
Underwater picture, as shown in formula (21):
In formulaFor enhanced underwater picture, so far then exportable enhanced underwater picture, underwater picture increase
Potent fruit is as shown in Figure 4.
For the validity for verifying this method, tested using multiple image.Atmosphere secretly schemes that test results are shown in figure 3,
The dark image of Fig. 3 the first behavior atmosphere, the second enhanced image of behavior the invention patent.There are brightness for original image secretly, contrast
The features such as low.After algorithm process, figure brightness and contrast is improved, and details is clear, the experimental results showed that this method can be mentioned effectively
The brightness of the high dark image of atmosphere.Test results are shown in figure 4 for underwater picture, Fig. 4 the first behavior underwater picture, second behavior this hair
The bright enhanced underwater picture of patent；Original image the features such as there are colour cast, atomization, low contrasts.It is underwater to scheme after algorithm process
As colour cast is corrected, contrast is greatly improved, the experimental results showed that this method also has preferable enhancing effect to underwater picture
Fruit.
Embodiment two
According to the one aspect of one or more other embodiments of the present disclosure, a kind of computer readable storage medium is provided.
A kind of computer readable storage medium, wherein being stored with a plurality of instruction, described instruction is suitable for by terminal device
Reason device load and a kind of described in executing is suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere.
Embodiment three
According to the one aspect of one or more other embodiments of the present disclosure, a kind of terminal device is provided.
A kind of terminal device comprising processor and computer readable storage medium, processor is for realizing each instruction；Meter
Calculation machine readable storage medium storing program for executing is suitable for being loaded by processor and being executed described one kind and is applicable in for storing a plurality of instruction, described instruction
In underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere.
These computer executable instructions execute the equipment according to each reality in the disclosure
Apply method or process described in example.
In the present embodiment, computer program product may include computer readable storage medium, containing for holding
The computer-readable program instructions of row various aspects of the disclosure.Computer readable storage medium, which can be, can keep and store
By the tangible device for the instruction that instruction execution equipment uses.Computer readable storage medium for example can be-- but it is unlimited
In-- storage device electric, magnetic storage apparatus, light storage device, electric magnetic storage apparatus, semiconductor memory apparatus or above-mentioned
Any appropriate combination.The more specific example (non exhaustive list) of computer readable storage medium includes: portable computing
Machine disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or
Flash memory), static random access memory (SRAM), Portable compressed disk read-only memory (CD-ROM), digital versatile disc
(DVD), memory stick, floppy disk, mechanical coding equipment, the punch card for being for example stored thereon with instruction or groove internal projection structure, with
And above-mentioned any appropriate combination.Computer readable storage medium used herein above is not interpreted instantaneous signal itself,
The electromagnetic wave of such as radio wave or other Free propagations, the electromagnetic wave propagated by waveguide or other transmission mediums (for example,
Pass through the light pulse of fiber optic cables) or pass through electric wire transmit electric signal.
Computer-readable program instructions described herein can be downloaded to from computer readable storage medium it is each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, local area network, wide area network and/or wireless network
Portion stores equipment.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, firewall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
Computer program instructions for executing present disclosure operation can be assembly instruction, instruction set architecture (ISA)
Instruction, machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programmings
The source code or object code that any combination of language is write, the programming language include the programming language-of object-oriented such as
C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer-readable program refers to
Order can be executed fully on the user computer, partly be executed on the user computer, as an independent software package
Execute, part on the user computer part on the remote computer execute or completely on a remote computer or server
It executes.In situations involving remote computers, remote computer can include local area network by the network-of any kind
(LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize internet
Service provider is connected by internet).In some embodiments, by being believed using the state of computer-readable program instructions
Breath comes personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or programmable logic
Array (PLA), the electronic circuit can execute computer-readable program instructions, to realize the various aspects of present disclosure.
Example IV
According to the one aspect of one or more other embodiments of the present disclosure, provide a kind of dark suitable for underwater picture and atmosphere
The dual-purpose image intensifier device of image.
It is a kind of suitable for underwater picture and the dual-purpose image intensifier device of the dark image of atmosphere, be suitable for based on described one kind
The dual-purpose image enchancing method of underwater picture and the dark image of atmosphere, comprising:
Image receiver module is configured as receiving the original image and ash of the dark image of underwater picture or atmosphere to image enhancement
Degree figure；
Reflectivity and incident light estimation module are configured as being estimated by the target equation of building, obtain reflectivity
Image and incident light images；
Reflectivity post-processing module is configured as enhancing albedo image degree of comparing, obtains the atmosphere of high brightness
Image；
Incident light post-processing module, is configured as carrying out colour correction to incident light images, enhances result in conjunction with contrast
The underwater picture enhanced.
It should be noted that although being referred to several modules or submodule of equipment in the detailed description above, it is this
Division is only exemplary rather than enforceable.In fact, in accordance with an embodiment of the present disclosure, two or more above-described moulds
The feature and function of block can embody in a module.Conversely, the feature and function of an above-described module can be with
Further division is to be embodied by multiple modules.
The foregoing is merely preferred embodiment of the present application, are not intended to limit this application, for the skill of this field
For art personnel, various changes and changes are possible in this application.Within the spirit and principles of this application, made any to repair
Change, equivalent replacement, improvement etc., should be included within the scope of protection of this application.Therefore, the present invention is not intended to be limited to this
These embodiments shown in text, and it is to fit to the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. a kind of suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere, which is characterized in that this method comprises:
Receive the original image and grayscale image of the dark image of underwater picture or atmosphere to image enhancement；
Estimated by the target equation of building, obtains albedo image and incident light images；
Albedo image degree of comparing is enhanced, the atmosphere image of high brightness is obtained；
Colour correction is carried out to incident light images, the underwater picture enhanced in conjunction with contrast enhancing result.
2. it is as described in claim 1 a kind of suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere, it is special
Sign is, in the method, the RGB triple channel to the underwater picture of image enhancement or the original image of the dark image of atmosphere is led to respectively
The target equation for crossing building is estimated.
3. it is as described in claim 1 a kind of suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere, it is special
Sign is, in the method, constructs the target equation according to Retinex theory, the target equation is reflectivity and incidence
The data of light keep item, the sparse regularization term of full variation, the data of reflectivity keep the data of item and incident light keep item it
With；The restrictive condition of the target equation is that reflectivity value range is [0 1]；
The data of the reflectivity and incident light keep item to indicate by the L2 norm that reflectivity and incident light product subtract original image；
The sparse regularization term of full variation is indicated by the L1 norm of gradient operator and reflectivity product；
The data of the reflectivity keep item to indicate by the L2 norm that reflectivity subtracts grayscale image；
The data of the incident light keep item to be mapped to by the Steerable filter that incident light subtracts original image by [0 1] intervals linear
The L2 norm in [0.2 1] section indicates.
4. it is as claimed in claim 3 a kind of suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere, it is special
Sign is, this method further include: be introduced into auxiliary variable Z, E and regulatory factor ρ to the full variation in the target equation
The L1 norm of sparse regularization term carries out equivalent transformation, and the transformed complete sparse regularization term of variation is auxiliary variable Z's
L1 norm and gradient operator and reflectivity product subtract auxiliary variable Z and add the L2 norm of auxiliary variable E and the product of regulatory factor ρ
The sum of.
5. it is as claimed in claim 4 a kind of suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere, it is special
Sign is, in the method, transformed target equation is decomposed into Z subproblem, R subproblem and I subproblem and is recycled repeatedly
In generation, solves, and is modified according to restrictive condition to reflectivity and incident light, obtains albedo image and incident light images.
6. it is as claimed in claim 5 a kind of suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere, it is special
Sign is that in the method, the Z subproblem is the entry deletion of Z will to be free of in transformed target equation, and grasp by shrinking
Make the optimal solution of export Z subproblem；
The R subproblem be by transformed target equation be free of R entry deletion, and by enable R partial derivative be 0, use
Fast Fourier Transform (FFT) is simultaneously solved in conjunction with convolution theorem, and the optimal solution of R subproblem is obtained；
The I subproblem be by transformed target equation be free of I entry deletion, and by enable I partial derivative be 0, obtain I
The optimal solution of subproblem.
7. it is as described in claim 1 a kind of suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere, it is special
Sign is, in the method, is enhanced its radio-frequency component degree of comparing using homomorphic filtering albedo image；
Colour correction is carried out using Gaussian Profile Linear Mapping to incident light images.
8. a kind of computer readable storage medium, wherein being stored with a plurality of instruction, which is characterized in that described instruction is suitable for by terminal
The processor of equipment is loaded and is executed as claim 1-7 is described in any item a kind of suitable for underwater picture and the dark image of atmosphere
Dual-purpose image enchancing method.
9. a kind of terminal device comprising processor and computer readable storage medium, processor is for realizing each instruction；It calculates
Machine readable storage medium storing program for executing is for storing a plurality of instruction, which is characterized in that described instruction is suitable for being loaded by processor and being executed such as power
Benefit requires 1-7 described in any item a kind of suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere.
10. a kind of suitable for underwater picture and the dual-purpose image intensifier device of the dark image of atmosphere, which is characterized in that based on such as right
It is required that 1-7 is described in any item a kind of suitable for underwater picture and the dual-purpose image enchancing method of the dark image of atmosphere, comprising:
Image receiver module is configured as receiving the original image and gray scale of the dark image of underwater picture or atmosphere to image enhancement
Figure；
Reflectivity and incident light estimation module are configured as being estimated by the target equation of building, obtain albedo image
And incident light images；
Reflectivity post-processing module is configured as enhancing albedo image degree of comparing, obtains the atmosphere image of high brightness；
Incident light post-processing module is configured as carrying out colour correction to incident light images, obtains in conjunction with contrast enhancing result
The underwater picture of enhancing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910453495.6A CN110175963B (en) | 2019-05-28 | 2019-05-28 | Dual-purpose image enhancement method and device suitable for underwater image and atmospheric dark image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910453495.6A CN110175963B (en) | 2019-05-28 | 2019-05-28 | Dual-purpose image enhancement method and device suitable for underwater image and atmospheric dark image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110175963A true CN110175963A (en) | 2019-08-27 |
| CN110175963B CN110175963B (en) | 2021-02-09 |
Family
ID=67695823
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910453495.6A Active CN110175963B (en) | 2019-05-28 | 2019-05-28 | Dual-purpose image enhancement method and device suitable for underwater image and atmospheric dark image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110175963B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110706180A (en) * | 2019-10-09 | 2020-01-17 | 山东大学 | Method, system, equipment and medium for improving visual quality of extremely dark image |
| CN111968188A (en) * | 2020-07-08 | 2020-11-20 | 华南理工大学 | Low-illumination image enhancement processing method, system, device and storage medium |
| CN116152116A (en) * | 2023-04-04 | 2023-05-23 | 青岛哈尔滨工程大学创新发展中心 | Underwater image enhancement method based on visual self-attention model |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101102399A (en) * | 2007-07-26 | 2008-01-09 | 上海交通大学 | Real time digital image processing and enhancing method with noise removal function |
| CN101303766A (en) * | 2008-07-09 | 2008-11-12 | 北京航空航天大学 | Method for rapidly reinforcing color image based on Retinex theory |
| CN101783012A (en) * | 2010-04-06 | 2010-07-21 | 中南大学 | Automatic image defogging method based on dark primary colour |
| CN102231791A (en) * | 2011-06-30 | 2011-11-02 | 北京云加速信息技术有限公司 | Video image defogging method based on image brightness stratification |
| CN103177424A (en) * | 2012-12-07 | 2013-06-26 | 西安电子科技大学 | Low-luminance image reinforcing and denoising method |
| CN107895357A (en) * | 2017-12-25 | 2018-04-10 | 北京航空航天大学 | A kind of real-time water surface thick fog scene image Enhancement Method based on FPGA |
-
2019
- 2019-05-28 CN CN201910453495.6A patent/CN110175963B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101102399A (en) * | 2007-07-26 | 2008-01-09 | 上海交通大学 | Real time digital image processing and enhancing method with noise removal function |
| CN101303766A (en) * | 2008-07-09 | 2008-11-12 | 北京航空航天大学 | Method for rapidly reinforcing color image based on Retinex theory |
| CN101783012A (en) * | 2010-04-06 | 2010-07-21 | 中南大学 | Automatic image defogging method based on dark primary colour |
| CN102231791A (en) * | 2011-06-30 | 2011-11-02 | 北京云加速信息技术有限公司 | Video image defogging method based on image brightness stratification |
| CN103177424A (en) * | 2012-12-07 | 2013-06-26 | 西安电子科技大学 | Low-luminance image reinforcing and denoising method |
| CN107895357A (en) * | 2017-12-25 | 2018-04-10 | 北京航空航天大学 | A kind of real-time water surface thick fog scene image Enhancement Method based on FPGA |
Non-Patent Citations (1)
| Title |
|---|
| XUEYANG FU ET AL: "A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation", 《IEEE TRANSACTIONS ON IMAGE PROCESSING》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110706180A (en) * | 2019-10-09 | 2020-01-17 | 山东大学 | Method, system, equipment and medium for improving visual quality of extremely dark image |
| CN110706180B (en) * | 2019-10-09 | 2022-02-11 | 山东大学 | Method, system, equipment and medium for improving visual quality of extremely dark image |
| CN111968188A (en) * | 2020-07-08 | 2020-11-20 | 华南理工大学 | Low-illumination image enhancement processing method, system, device and storage medium |
| CN111968188B (en) * | 2020-07-08 | 2023-08-22 | 华南理工大学 | Low-light image enhancement processing method, system, device and storage medium |
| CN116152116A (en) * | 2023-04-04 | 2023-05-23 | 青岛哈尔滨工程大学创新发展中心 | Underwater image enhancement method based on visual self-attention model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110175963B (en) | 2021-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bavirisetti et al. | Multi-scale guided image and video fusion: A fast and efficient approach | |
| Zhang et al. | Single image defogging based on multi-channel convolutional MSRCR | |
| CN110175963A (en) | It is a kind of suitable for underwater picture and the dual-purpose image enchancing method and device of the dark image of atmosphere | |
| CN110163818A (en) | A kind of low illumination level video image enhancement for maritime affairs unmanned plane | |
| CN109064436A (en) | Image interfusion method | |
| CN106920221A (en) | Take into account the exposure fusion method that Luminance Distribution and details are presented | |
| CN109215025B (en) | Infrared weak and small target detection method based on non-convex rank approach minimization | |
| CN113962877B (en) | Pixel distortion correction method, correction device and terminal | |
| Xi et al. | Super resolution reconstruction algorithm of video image based on deep self encoding learning | |
| CN113554739A (en) | Relighting image generation method and device and electronic equipment | |
| Zhang et al. | Research on engineering vehicle target detection in aerial photography environment based on YOLOX | |
| Cornejo et al. | Bipolar fuzzy relation equations based on the product T-norm | |
| CN113610735A (en) | Hybrid noise removing method for infrared image of power equipment | |
| Ang et al. | Noise-aware zero-reference low-light image enhancement for object detection | |
| Fu et al. | Wavelet-based retinex algorithm for unmanned aerial vehicle image defogging | |
| Ngo et al. | A new data preparation methodology in machine learning-based haze removal algorithms | |
| CN113191958B (en) | Image denoising method based on robust tensor low-rank representation | |
| Ruchay et al. | Removal of impulsive noise from color images with cascade switching algorithm | |
| Qiu et al. | Adaptive uneven illumination correction method for autonomous live-line maintenance robot | |
| Fan et al. | Sharp processing of blur image based on generative adversarial network | |
| CN104574343B (en) | The method and apparatus of image is extracted in a kind of video | |
| CN114418064A (en) | Target detection method, terminal equipment and storage medium | |
| CN118426736B (en) | Bionic compound eye type multispectral target detection system and method for severe environment | |
| CN111191593A (en) | Image target detection method and device, storage medium and sewage pipeline detection device | |
| CN116091367B (en) | Blind deblurring method, device, equipment and medium for optical remote sensing image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |